Dense feed-forward neural networks over floats can be presented as coherent categories G whose Set-models are the networks, with inference as precomposition along a coherent functor from a span category.
Sheaves in Geometry and Logic
4 Pith papers cite this work, alongside 385 external citations. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
Constructs crossed-product von Neumann algebras M_u from incompressible flows to define commutator-based tracial complexity functionals linked to determinants and entropy.
This paper overviews monads in 2-categories and defines two new double categories of monads extending Lack and Street's 2-categories of monads.
Kochen-Specker contextuality generalizes nonclassicality while Spekkens' noncontextuality generalizes classicality, reconciling the two as successive stages in a hierarchy of classicality.
citing papers explorer
-
Presenting Neural Networks via Coherent Functors
Dense feed-forward neural networks over floats can be presented as coherent categories G whose Set-models are the networks, with inference as precomposition along a coherent functor from a span category.
-
Crossed-Product von Neumann Algebras for Incompressible Navier--Stokes Flows and Spectral Complexity Indicators
Constructs crossed-product von Neumann algebras M_u from incompressible flows to define commutator-based tracial complexity functionals linked to determinants and entropy.
-
Monads in 2-categories
This paper overviews monads in 2-categories and defines two new double categories of monads extending Lack and Street's 2-categories of monads.
-
Warring Contextualities -- Provably Classical vs Provably Nonclassical
Kochen-Specker contextuality generalizes nonclassicality while Spekkens' noncontextuality generalizes classicality, reconciling the two as successive stages in a hierarchy of classicality.